© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14317
    Prev
    Next
    INDEX
    Explanations

    alike, once

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Se
    0.65
    field
    0.63
    v
    0.62
    P
    0.62
     Babu
    0.59
    Се
    0.57
    hov
    0.55
    Before
    0.55
    Sor
    0.55
    Тре
    0.54
    POSITIVE LOGITS
     사용하는
    0.54
     simultaneously
    0.52
     Simultaneously
    0.52
     دہشت
    0.50
    害怕
    0.48
     Axial
    0.47
     사용하여
    0.47
     Simultaneous
    0.47
    龈
    0.47
     kDa
    0.47
    Activations Density 0.053%

    No Known Activations